Synopses & Reviews
The study of machine learning within the mathematical framework of complexity theory has seen great strides in just a few short years, spurred on by the tremendous rise in interest from engineers studying control to analysts predicting financial market activity. Based on the first European Conference on Computational Learning Theory, and including a number of invited contributions, Computational Learning Theory offers an outstanding overview of the subject, with topics ranging from results inspired by neural network research to those originating from more classical artificial intelligence approaches. It will appeal to students and researchers in applied mathematics, computer science, and cognitive science.
Table of Contents
PART I: Invited Papers
1. On the Complexity of Learning on Neural Nets, W. Maass
2. Some New Directions in Computational Learning Theory, M. Frazier and L. Pitt
3. A Neuroidal Model for Cognitive Functions, L.G. Valiant
PART II: Contributed Papers
4. Learning Rules with Local Exceptions, J. Kivinen, H. Mannila and E. Ukkonen
5. On Learning Simple Deterministic and Probabilistic Neural Concepts, M. Golea and M. Marchand
6. Learning Unions of Convex Polygons, P. Fischer
7. On Training Simple Neural Networks and Small-Weight Neurons, T. Hegedus
8. Bounds on the Number of Examples Needed for Learning Functions, H.U. Simon
9. Valid Generalization of Functions from Close Approximations on a Sample, M. Anthony and J. Shawe-Taylor
10. Using Experts for Predicting Continuous Outcomes, J. Kivinen and M.K. Warmuth
11. Read-Twice DNF Formulas are Properly Learnable, K. Pillaipakkamnatt and V. Raghavan
12. Trial and Error: A New Approach to Space-bounded Learning, F. Ameur, P. Fischer, K.-U. Hoffgen and F. Meyer auf der Heide
13. Using Kullback-Leibler Divergence in Learning Theory, S. Anoulova and S. Polt
14. Learning Local and Recognizable W-Languages and Monadic Logic Programs, Saoudi and T. Yokomori
15. Classification of Predicates and Languages, R. Wiehagen, C.H. Smith and T. Zeugmann
16. The Neural Network Loading Problem is Undecidable, H. Wiklicky
17. On the Power of Equivalence, R. Gavalda
18. On-line Prediction and Conversion Strategies
19. Learning Non-parametric Smooth Rules by Stochastic Rules with Finite Partitioning, K. Yamanishi
20. Improved Sample Size Nounds for PAB-Decisions, S. Polt